mradermacher/qwen3-coder-reap-25b-a3b-i1-gguf overview

{
  "metadata": {},
  "card_data": {
    "base_model": "cerebras/Qwen3-Coder-REAP-25B-A3B",
    "language": [
      "en"
    ],
    "library_name": "transformers",
    "license": "apache-2.0",
    "license_link": "https://huggingface.co/cerebras/Qwen3-Coder-REAP-25B-A3B/blob/main/LICENSE",
    "mradermacher": {
      "readme_rev": 1
    },
    "quantized_by": "mradermacher",
    "tags": [
      "qwen-coder",
      "MOE",
      "pruning",
      "compression"
    ],
    "frontmatter": {
      "base_model": "cerebras/Qwen3-Coder-REAP-25B-A3B",
      "language": [
        "en"
      ],
      "library_name": "transformers",
      "license": "apache-2.0",
      "license_link": "https://huggingface.co/cerebras/Qwen3-Coder-REAP-25B-A3B/blob/main/LICENSE",
      "mradermacher": [],
      "quantized_by": "mradermacher",
      "tags": [
        "qwen-coder",
        "MOE",
        "pruning",
        "compression"
      ]
    },
    "hero_image_url": "https://www.nethype.de/huggingface_embed/quantpplgraph.png",
    "summary": "## About         weighted/imatrix quants of https://huggingface.co/cerebras/Qwen3-Coder-REAP-25B-A3B  ***For a convenient overview and download list, visit our model page for this model.*** static quants are available at https://huggingface.co/mradermacher/Qwen3-Coder-REAP-25B-A3B-GGUF",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nbase_model: cerebras/Qwen3-Coder-REAP-25B-A3B\nlanguage:\n- en\nlibrary_name: transformers\nlicense: apache-2.0\nlicense_link: https://huggingface.co/cerebras/Qwen3-Coder-REAP-25B-A3B/blob/main/LICENSE\nmradermacher:\n  readme_rev: 1\nquantized_by: mradermacher\ntags:\n- qwen-coder\n- MOE\n- pruning\n- compression\n---\n## About\n\n<!-- ### quantize_version: 2 -->\n<!-- ### output_tensor_quantised: 1 -->\n<!-- ### convert_type: hf -->\n<!-- ### vocab_type:  -->\n<!-- ### tags: nicoboss -->\n<!-- ### quants:  Q2_K IQ3_M Q4_K_S IQ3_XXS Q3_K_M small-IQ4_NL Q4_K_M IQ2_M Q6_K IQ4_XS Q2_K_S IQ1_M Q3_K_S IQ2_XXS Q3_K_L IQ2_XS Q5_K_S IQ2_S IQ1_S Q5_K_M Q4_0 IQ3_XS Q4_1 IQ3_S -->\n<!-- ### quants_skip:  -->\n<!-- ### skip_mmproj:  -->\nweighted/imatrix quants of https://huggingface.co/cerebras/Qwen3-Coder-REAP-25B-A3B\n\n<!-- provided-files -->\n\n***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-Coder-REAP-25B-A3B-i1-GGUF).***\n\nstatic quants are available at https://huggingface.co/mradermacher/Qwen3-Coder-REAP-25B-A3B-GGUF\n## Usage\n\nIf you are unsure how to use GGUF files, refer to one of [TheBloke's\nREADMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for\nmore details, including on how to concatenate multi-part files.\n\n## Provided Quants\n\n(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)\n\n| Link | Type | Size/GB | Notes |\n|:-----|:-----|--------:|:------|\n| [GGUF](https://huggingface.co/mradermacher/Qwen3-Coder-REAP-25B-A3B-i1-GGUF/resolve/main/Qwen3-Coder-REAP-25B-A3B.imatrix.gguf) | imatrix | 0.2 | imatrix file (for creating your own quants) |\n| [GGUF](https://huggingface.co/mradermacher/Qwen3-Coder-REAP-25B-A3B-i1-GGUF/resolve/main/Qwen3-Coder-REAP-25B-A3B.i1-IQ1_S.gguf) | i1-IQ1_S | 5.4 | for the desperate |\n| [GGUF](https://huggingface.co/mradermacher/Qwen3-Coder-REAP-25B-A3B-i1-GGUF/resolve/main/Qwen3-Coder-REAP-25B-A3B.i1-IQ1_M.gguf) | i1-IQ1_M | 5.9 | mostly desperate |\n| [GGUF](https://huggingface.co/mradermacher/Qwen3-Coder-REAP-25B-A3B-i1-GGUF/resolve/main/Qwen3-Coder-REAP-25B-A3B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 6.8 |  |\n| [GGUF](https://huggingface.co/mradermacher/Qwen3-Coder-REAP-25B-A3B-i1-GGUF/resolve/main/Qwen3-Coder-REAP-25B-A3B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 7.5 |  |\n| [GGUF](https://huggingface.co/mradermacher/Qwen3-Coder-REAP-25B-A3B-i1-GGUF/resolve/main/Qwen3-Coder-REAP-25B-A3B.i1-IQ2_S.gguf) | i1-IQ2_S | 7.7 |  |\n| [GGUF](https://huggingface.co/mradermacher/Qwen3-Coder-REAP-25B-A3B-i1-GGUF/resolve/main/Qwen3-Coder-REAP-25B-A3B.i1-IQ2_M.gguf) | i1-IQ2_M | 8.4 |  |\n| [GGUF](https://huggingface.co/mradermacher/Qwen3-Coder-REAP-25B-A3B-i1-GGUF/resolve/main/Qwen3-Coder-REAP-25B-A3B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 8.7 | very low quality |\n| [GGUF](https://huggingface.co/mradermacher/Qwen3-Coder-REAP-25B-A3B-i1-GGUF/resolve/main/Qwen3-Coder-REAP-25B-A3B.i1-Q2_K.gguf) | i1-Q2_K | 9.3 | IQ3_XXS probably better |\n| [GGUF](https://huggingface.co/mradermacher/Qwen3-Coder-REAP-25B-A3B-i1-GGUF/resolve/main/Qwen3-Coder-REAP-25B-A3B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 9.8 | lower quality |\n| [GGUF](https://huggingface.co/mradermacher/Qwen3-Coder-REAP-25B-A3B-i1-GGUF/resolve/main/Qwen3-Coder-REAP-25B-A3B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 10.4 |  |\n| [GGUF](https://huggingface.co/mradermacher/Qwen3-Coder-REAP-25B-A3B-i1-GGUF/resolve/main/Qwen3-Coder-REAP-25B-A3B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 10.9 | IQ3_XS probably better |\n| [GGUF](https://huggingface.co/mradermacher/Qwen3-Coder-REAP-25B-A3B-i1-GGUF/resolve/main/Qwen3-Coder-REAP-25B-A3B.i1-IQ3_S.gguf) | i1-IQ3_S | 11.0 | beats Q3_K* |\n| [GGUF](https://huggingface.co/mradermacher/Qwen3-Coder-REAP-25B-A3B-i1-GGUF/resolve/main/Qwen3-Coder-REAP-25B-A3B.i1-IQ3_M.gguf) | i1-IQ3_M | 11.1 |  |\n| [GGUF](https://huggingface.co/mradermacher/Qwen3-Coder-REAP-25B-A3B-i1-GGUF/resolve/main/Qwen3-Coder-REAP-25B-A3B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 12.1 | IQ3_S probably better |\n| [GGUF](https://huggingface.co/mradermacher/Qwen3-Coder-REAP-25B-A3B-i1-GGUF/resolve/main/Qwen3-Coder-REAP-25B-A3B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 13.1 | IQ3_M probably better |\n| [GGUF](https://huggingface.co/mradermacher/Qwen3-Coder-REAP-25B-A3B-i1-GGUF/resolve/main/Qwen3-Coder-REAP-25B-A3B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 13.5 |  |\n| [GGUF](https://huggingface.co/mradermacher/Qwen3-Coder-REAP-25B-A3B-i1-GGUF/resolve/main/Qwen3-Coder-REAP-25B-A3B.i1-Q4_0.gguf) | i1-Q4_0 | 14.3 | fast, low quality |\n| [GGUF](https://huggingface.co/mradermacher/Qwen3-Coder-REAP-25B-A3B-i1-GGUF/resolve/main/Qwen3-Coder-REAP-25B-A3B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 14.3 | optimal size/speed/quality |\n| [GGUF](https://huggingface.co/mradermacher/Qwen3-Coder-REAP-25B-A3B-i1-GGUF/resolve/main/Qwen3-Coder-REAP-25B-A3B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 15.2 | fast, recommended |\n| [GGUF](https://huggingface.co/mradermacher/Qwen3-Coder-REAP-25B-A3B-i1-GGUF/resolve/main/Qwen3-Coder-REAP-25B-A3B.i1-Q4_1.gguf) | i1-Q4_1 | 15.7 |  |\n| [GGUF](https://huggingface.co/mradermacher/Qwen3-Coder-REAP-25B-A3B-i1-GGUF/resolve/main/Qwen3-Coder-REAP-25B-A3B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 17.3 |  |\n| [GGUF](https://huggingface.co/mradermacher/Qwen3-Coder-REAP-25B-A3B-i1-GGUF/resolve/main/Qwen3-Coder-REAP-25B-A3B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 17.8 |  |\n| [GGUF](https://huggingface.co/mradermacher/Qwen3-Coder-REAP-25B-A3B-i1-GGUF/resolve/main/Qwen3-Coder-REAP-25B-A3B.i1-Q6_K.gguf) | i1-Q6_K | 20.5 | practically like static Q6_K |\n\nHere is a handy graph by ikawrakow comparing some lower-quality quant\ntypes (lower is better):\n\n![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)\n\nAnd here are Artefact2's thoughts on the matter:\nhttps://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9\n\n## FAQ / Model Request\n\nSee https://huggingface.co/mradermacher/model_requests for some answers to\nquestions you might have and/or if you want some other model quantized.\n\n## Thanks\n\nI thank my company, [nethype GmbH](https://www.nethype.de/), for letting\nme use its servers and providing upgrades to my workstation to enable\nthis work in my free time. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.\n\n<!-- end -->\n",
    "related_quantizations": []
  },
  "tags": [
    "transformers",
    "gguf",
    "qwen-coder",
    "MOE",
    "pruning",
    "compression",
    "en",
    "base_model:cerebras/Qwen3-Coder-REAP-25B-A3B",
    "base_model:quantized:cerebras/Qwen3-Coder-REAP-25B-A3B",
    "license:apache-2.0",
    "endpoints_compatible",
    "region:us",
    "imatrix",
    "conversational"
  ],
  "likes": 2,
  "downloads": 780,
  "gated": false,
  "private": false,
  "last_modified": "2025-12-08T23:49:40.000Z",
  "created_at": "2025-10-21T16:24:57.000Z",
  "pipeline_tag": "",
  "library_name": "transformers"
}

{
  "_id": "68f7b3d9cb59141d7bff21d1",
  "id": "mradermacher/Qwen3-Coder-REAP-25B-A3B-i1-GGUF",
  "modelId": "mradermacher/Qwen3-Coder-REAP-25B-A3B-i1-GGUF",
  "sha": "599fab0a22b3276f511dae64882bb1049f28619d",
  "createdAt": "2025-10-21T16:24:57.000Z",
  "lastModified": "2025-12-08T23:49:40.000Z",
  "author": "mradermacher",
  "downloads": 780,
  "likes": 2,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "transformers",
  "siblings_count": 26
}